Ricci-Filtration: Boosting Retrieval-Augmented Generation Reranker to Query-Answer Tasks by Discrete Ricci Flow

  • 类型:arxiv
  • 标识:2606.15482
  • 链接:http://arxiv.org/abs/2606.15482v1
  • 主分类:rag
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:It is theoretically prove that normalized discrete Ricci flow can detect community structures by identifying distinct asymptotic behaviors in edge weights, and supports the removal of ``noisy''document chunks characterized by large weights and negative Ricci curvature relative to the query node.
  • OpenAlex ID:W7164903319
  • OpenAlex DOI:10.48550/arxiv.2606.15482
  • DOI:10.48550/arxiv.2606.15482
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2606.15482
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:Ricci-Filtration:通过离散 Ricci Flow 将 RAG 重排序器提升至 Query-Answer 任务
  • TLDR中文:本文理论上证明,归一化离散 Ricci Flow 可通过识别边权中的不同渐近行为来检测社区结构,并支持移除相对于 query 节点具有大权重与负 Ricci 曲率的"噪声"文档片段。
  • 来源文件
  • /inbox/tom/_candidates/2026-06-17-rag-retrieval-reranking-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]